© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15791
    Prev
    Next
    INDEX
    Explanations

    Oscar nominations and awards for performances

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ñģами
    -0.23
    maj
    -0.21
    วà¸ģ
    -0.21
    害
    -0.21
     CLOSED
    -0.21
    ILES
    -0.20
    RIES
    -0.19
    åijĽ
    -0.19
    太快
    -0.19
    éħįæĸ¹
    -0.18
    POSITIVE LOGITS
    饰æ¼Ķ
    0.20
    ä¸ĩ人
    0.20
    unist
    0.20
     Bust
    0.19
    åĶ¯ä¸Ģ
    0.19
    第ä¸ī人
    0.19
    _MP
    0.19
    ä¸Ģ人
    0.18
    广çĶµ
    0.18
    æłĩ注
    0.18
    Activations Density 0.021%

    No Known Activations